Automatic text segmentation and text recognition for video indexing
Multimedia Systems
Superresolution of License Plates in Real Traffic Videos
IEEE Transactions on Intelligent Transportation Systems
Hi-index | 0.00 |
This paper describes a vision-based car distance measuring system capable of telling the driver the gap distance between the host vehicle and the vehicle in front. The aim is to increase the road safety by warning the driver if the driving distance is too close and therefore can cause dangerous situation, and hence provide comfort driving condition for car users. The system uses the size of number plate characters to determine the distance. With the help of an image preprocessing stage, the region of interest (ROI) in the acquired images is identified. The ROI is then examined by a rule-based algorithm that identifies the characters in the plate and computes the corresponding height of the plate characters and thus the distance between the cars. Finally, in order to reduce the complexity of the algorithm, we propose a number plate tracking technique that continuously tracks and computes the height of the characters. We show the system working in real situations and results are discussed.